Improving Deep Learning Models via Constraint-Based Domain Knowledge: a Brief Survey

TL;DR

This survey reviews methods for integrating domain knowledge as constraints into deep learning models to enhance their performance, especially when data is scarce or complex functions are involved.

Contribution

It categorizes and summarizes five main approaches for incorporating domain knowledge into deep neural networks, providing a comprehensive overview of current techniques.

Findings

Five main categories of constraint-based domain knowledge integration identified

Constraint-based methods improve deep learning performance in data-scarce scenarios

Survey highlights future research directions in knowledge-guided deep learning

Abstract

Deep Learning (DL) models proved themselves to perform extremely well on a wide variety of learning tasks, as they can learn useful patterns from large data sets. However, purely data-driven models might struggle when very difficult functions need to be learned or when there is not enough available training data. Fortunately, in many domains prior information can be retrieved and used to boost the performance of DL models. This paper presents a first survey of the approaches devised to integrate domain knowledge, expressed in the form of constraints, in DL learning models to improve their performance, in particular targeting deep neural networks. We identify five (non-mutually exclusive) categories that encompass the main approaches to inject domain knowledge: 1) acting on the features space, 2) modifications to the hypothesis space, 3) data augmentation, 4) regularization schemes, 5) constrained learning.